ocr-and-documents

Name: ocr-and-documents
Availability: InStock
Author: garrettroi

Extract text and structured data from PDFs, scans, and images.

Updated Mar 12, 2026

Search Tags:#ocr #document processing #data extraction #pdf #text extraction #scanned documents

Ready to run

npx skills add https://github.com/GarrettRoi/open-manus --skill ocr-and-documents-garrettroi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/GarrettRoi/open-manus/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/GarrettRoi/open-manus --skill ocr-and-documents-garrettroi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pymupdf4llm, marker-pdf, python-docx, python-pptx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of text and data from various document formats, including PDFs, scanned documents, and images, eliminating manual data entry and content retrieval.

Core Features & Use Cases

Text Extraction: Extracts plain text from text-based PDFs.
OCR for Scanned Documents: Utilizes Optical Character Recognition for extracting text from images and scanned PDFs.
Table and Data Extraction: Parses and extracts structured data from tables within documents.
Remote URL Processing: Can process documents directly from web URLs using web_extract.
Use Case: Automatically extract all text and tables from a batch of scanned research papers or a collection of PDF invoices.

Quick Start

Use the ocr-and-documents skill to extract all text from the file 'report.pdf'.

Frequently Asked Questions about ocr-and-documents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text from scanned PDF documents?▼

To extract text from scanned PDFs, this skill uses marker-pdf for Optical Character Recognition. It processes images within the document to retrieve text, eliminating manual data entry from scanned files.

Can I extract text from a PDF hosted at a remote URL?▼

Yes, you can extract text from a PDF at a remote URL. The skill uses the web_extract function to fetch and process documents directly from web links without needing local files.

Does this tool support data extraction from tables in PDFs?▼

Yes, this tool supports data extraction from tables in PDFs. It parses structured data from tables within documents using pymupdf and marker-pdf, capturing both text and table layouts.

How do I extract text from DOCX and PPTX files?▼

To extract text from DOCX files, the skill uses the python-docx library. For PPTX files, it leverages python-pptx via the powerpoint skill to retrieve presentation text content.

What is the best way to parse text-based PDFs without OCR?▼

For text-based PDFs, the best way to parse text without OCR is using pymupdf. It directly extracts plain text from the document layer, skipping image recognition for faster retrieval.

Does this skill work with pymupdf for document processing?▼

Yes, this skill works with pymupdf for document processing. It relies on pymupdf and pymupdf4llm to extract text and structured data from text-based PDF documents efficiently.